create_draft

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations are all false, so the description must carry behavioral context. It discloses that HTML is constrained (rejects remote resources, hidden content, message-box escapes), preserves empty paragraphs, and cannot send. These details add value beyond annotations and do not contradict them. It stops short of discussing result side-effects or failure modes, but is reasonably transparent.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is three sentences in length, opens with the core action, and delivers key constraints efficiently. Every sentence adds meaningful information without repetition or filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's complexity (9 parameters, 0% schema coverage), the description is inadequate. It fails to explain most required and optional parameters, so an agent cannot confidently construct correct calls. The presence of an output schema doesn't compensate for missing parameter semantics. Only the HTML-related behavior is covered.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

With 0% schema description coverage, the description must compensate for all 9 parameters. It only touches on the html_body parameter through 'authored HTML' constraints and vaguely references content preservation. It offers no guidance on account_id, to, subject, body, cc, bcc, attachment_names, or reply_to_message, leaving most parameters poorly specified.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description opens with 'Save a draft' – a specific verb and resource. It also clarifies 'No send capability,' which disambiguates from any sending tool. However, it does not explicitly differentiate from the sibling 'update_draft,' so it falls short of a 5.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no explicit guidance on when to use this tool versus alternatives like update_draft. The only hint is 'No send capability,' which implicitly rules out sending but doesn't name alternatives or conditions for selection. This leaves the agent to infer usage context.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.